Your AI. Your machine.
A privacy-first, GPU-accelerated chat application that runs large language models entirely on your Windows PC. No cloud required.
Install
Download MSIX from Releases → double-click → launch
Build
git clone … && dotnet restore && dotnet build
Run
dotnet run --project src/InControl.App
Features
Local AI chat that respects your privacy.
Private by default
Your conversations never leave your computer. All data stored locally — no cloud, no telemetry.
RTX-accelerated
Built for NVIDIA GPUs with CUDA acceleration. Targets RTX 3060+ with 8–16GB VRAM.
Native Windows
WinUI 3 with Fluent Design. Looks and feels like a real Windows app, not an Electron wrapper.
Multi-backend
Ollama, llama.cpp, or bring your own. Swap backends without changing your workflow.
Markdown rendering
Rich text, code blocks, and syntax highlighting in every response.
NuGet libraries
Core and Inference packages available on NuGet for building your own local AI integrations.
Installation
From Release (recommended)
# 1. Download latest MSIX from GitHub Releases
# 2. Double-click to install
# 3. Launch from Start Menu
# Prerequisite: Ollama
# https://ollama.ai/download
ollama pull llama3.2
ollama serveFrom Source
git clone https://github.com/mcp-tool-shop-org/InControl-Desktop.git
cd InControl-Desktop
dotnet restore
dotnet build
# Run (requires Ollama running locally)
dotnet run --project src/InControl.AppNuGet Packages
Add packages
dotnet add package InControl.Core
dotnet add package InControl.InferenceUse in your app
// Stream chat with a local LLM
var client = inferenceClientFactory.Create("ollama");
await foreach (var token in client.StreamChatAsync(messages))
{
Console.Write(token);
}